Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4986 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.6733. Min Act: -0.0000

Data Index: 131298 (The Pile)

Max Activating Token Index: 84

Text #1

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5370. Min Act: -0.0000

Data Index: 1627571 (The Pile)

Max Activating Token Index: 954

Text #2

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5056. Min Act: -0.0000

Data Index: 497151 (The Pile)

Max Activating Token Index: 333

Text #3

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5450. Min Act: -0.0000

Data Index: 649635 (The Pile)

Max Activating Token Index: 704

Text #4

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4783. Min Act: -0.0000

Data Index: 1896544 (The Pile)

Max Activating Token Index: 285

Text #5

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4384. Min Act: -0.0000

Data Index: 747558 (The Pile)

Max Activating Token Index: 127

Text #6

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1044190 (The Pile)

Max Activating Token Index: 886

Text #7

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1267215 (The Pile)

Max Activating Token Index: 337

Text #8

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1521409 (The Pile)

Max Activating Token Index: 1019

Text #9

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4501. Min Act: -0.0000

Data Index: 381481 (The Pile)

Max Activating Token Index: 513

Text #10

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4638. Min Act: -0.0000

Data Index: 1208095 (The Pile)

Max Activating Token Index: 306

Text #11

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.3961. Min Act: -0.0000

Data Index: 321035 (The Pile)

Max Activating Token Index: 270

Text #12

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1139849 (The Pile)

Max Activating Token Index: 665

Text #13

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4363. Min Act: -0.0000

Data Index: 46036 (The Pile)

Max Activating Token Index: 767

Text #14

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4324. Min Act: -0.0000

Data Index: 150990 (The Pile)

Max Activating Token Index: 401

Text #15

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4568. Min Act: -0.0000

Data Index: 432668 (The Pile)

Max Activating Token Index: 166

Text #16

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1591584 (The Pile)

Max Activating Token Index: 743

Text #17

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4057. Min Act: -0.0000

Data Index: 634704 (The Pile)

Max Activating Token Index: 341

Text #18

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1848957 (The Pile)

Max Activating Token Index: 423

Text #19

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4026. Min Act: -0.0000

Data Index: 812841 (The Pile)

Max Activating Token Index: 845